metadata
base_model: Qwen/Qwen2.5-32B-Instruct
library_name: peft
pipeline_tag: text-generation
tags:
- lora
- sft
- dpo
- coding
- eu-trained
- transformers
- trl
license: apache-2.0
Kode 32B LoRA Adapter
LoRA adapter (r=64, alpha=128) trained with DPO+SFT on production code samples.
- Base model: Qwen/Qwen2.5-32B-Instruct
- Training: Claude-generated code samples on A100 80GB
- Languages: Rust, Go, TypeScript, Python, C#, SQL, Tailwind
- License: Apache 2.0
Usage
from peft import PeftModel
from transformers import AutoModelForCausalLM
base = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2.5-32B-Instruct")
model = PeftModel.from_pretrained(base, "SimpleLLM/kode-32b-lora")
Hosted inference available at SimpleLLM.eu